WO2022088018A1 - Positioning method, apparatus, device and system, and storage medium - Google Patents

Abstract

The present application relates to a positioning method, apparatus, device and system, and a storage medium. The method comprises: acquiring a moment at which positioning is to be performed, wherein said moment is an IMU sampling moment of an IMU mounted on a positioning device; acquiring an IMU output value of the IMU at said moment; when a first measurement signal from a 5G base station is received within a first predetermined time interval around said moment, determining positioning information of the positioning device on the basis of the IMU output value and the first measurement signal; and when a second measurement signal from a navigation satellite is received within a second predetermined time interval around said moment, determining positioning information of the positioning device on the basis of the IMU output value and the second measurement signal.

Description

Positioning method, apparatus, device, system and storage medium technical field

The present application relates to the field of positioning technology, and in particular, to a positioning method, apparatus, device, system, and storage medium.

Background technique

Positioning technology is widely used in various devices that need to estimate their own position, attitude, etc., such as mobile phones, tablet computers, vehicles, and so on.

Positioning technology includes satellite navigation technology, Ultra Wide Band (UWB) technology, etc. Among them, satellite navigation technology has high positioning accuracy in open areas such as outdoor, but indoors will lead to low positioning accuracy due to insufficient signal. The technology can achieve high-precision indoor positioning, but the outdoor positioning ability is weak.

Positioning can be improved by combining different positioning technologies, such as using ultra-broadband technology for positioning indoors, and using satellite navigation technology for positioning in outdoor open areas, but both are carried out in indoor or outdoor local spaces. Positioning, and the connection between the two indoors and outdoors is poor. When the equipment that needs to be positioned is turned from indoors to outdoors, or from outdoor to indoors, the positioning will have a large jump, and continuous high-precision positioning in space cannot be achieved.

Therefore, there is still room for improvement in the above positioning technology.

SUMMARY OF THE INVENTION

Based on this, it is necessary to provide a positioning method, apparatus, device, system and storage medium.

On the one hand, a positioning method is provided, comprising: obtaining the moment to be positioned; obtaining an IMU output value of an inertial measurement unit (Inertial Measurement Unit, IMU) loaded on the positioning device at the moment to be positioned; When the first measurement signal from the 5G base station is received within the time interval, the positioning information of the positioning device is determined based on the IMU output value and the first measurement signal; During the second measurement signal, the positioning information of the positioning device is determined based on the IMU output value and the second measurement signal.

On the other hand, a positioning device is provided, comprising: a time acquisition module for acquiring the time to be positioned; an IMU value acquisition module for acquiring the IMU output value of the IMU loaded on the positioning device at the time to be positioned; a first positioning module , used to determine the positioning information of the positioning device based on the IMU output value and the first measurement signal when the first measurement signal from the 5G base station is received within the first predetermined time interval around the moment to be positioned; and the second positioning module, When the second measurement signal from the navigation satellite is received in the second predetermined time interval around the time to be positioned, the positioning information of the positioning device is determined based on the output value of the IMU and the second measurement signal.

On the other hand, a positioning device is provided, including an IMU module, a 5G module, a satellite positioning module, a memory and a processor, wherein the IMU module, the 5G module, the satellite positioning module and the memory are respectively connected to the processor; the IMU module obtains at the time of IMU sampling The IMU output value of the positioning device, and output the IMU output value to the processor; the 5G module receives the first measurement signal of the uplink reference signal of the positioning device measured by the 5G base station at the 5G sampling time from the 5G base station, and sends the first measurement signal to the output to the processor; the satellite positioning module receives the second measurement signal of the positioning device observed by the navigation satellite at the satellite sampling time from the navigation satellite, and outputs the second measurement signal to the processor; the memory stores a computer program; and the processor executes The computer program implements the following methods: obtaining the time to be positioned; obtaining the IMU output value of the IMU loaded on the positioning device at the time to be positioned; when receiving the first measurement signal from the 5G base station within the first predetermined time interval around the time to be positioned , determine the positioning information of the positioning device based on the IMU output value and the first measurement signal; when receiving the second measurement signal from the navigation satellite within the second predetermined time interval around the time to be positioned, based on the IMU output value and the second measurement signal Measure the signal to determine the positioning information of the positioning device.

On the other hand, a positioning system is provided, including a 5G base station, a navigation satellite and a positioning device, the positioning device is respectively connected to the navigation satellite and the 5G base station in communication; the 5G base station measures the first measurement signal of the uplink reference signal of the positioning device at the 5G sampling time , and send the first measurement signal to the positioning device; the navigation satellite observes the second measurement signal of the positioning device at the satellite sampling time, and outputs the second measurement signal to the positioning device; the positioning device performs the following methods: obtaining the time to be positioned; obtaining The IMU output value of the IMU loaded on the positioning device at the moment to be positioned; when the first measurement signal from the 5G base station is received within the first predetermined time interval around the moment to be positioned, based on the output value of the IMU and the first measurement signal, determine The positioning information of the positioning device; when the second measurement signal from the navigation satellite is received within the second predetermined time interval around the time to be positioned, the positioning information of the positioning device is determined based on the IMU output value and the second measurement signal.

On the other hand, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following methods are implemented: obtaining the time to be positioned; obtaining the IMU output of the IMU loaded on the positioning device at the time to be positioned value; when the first measurement signal from the 5G base station is received within the first predetermined time interval around the moment to be positioned, the positioning information of the positioning device is determined based on the IMU output value and the first measurement signal; when the first measurement signal is received around the moment to be positioned When the second measurement signal from the navigation satellite is received within two predetermined time intervals, the positioning information of the positioning device is determined based on the output value of the IMU and the second measurement signal.

The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below. Other features, objects and advantages of the present application will become apparent from the description, drawings and claims.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings that are used in the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, the drawings of other embodiments can also be obtained according to these drawings without creative effort.

FIG. 1 is a schematic diagram of the effective spatial coverage of the BDS, 5G, and UWB positioning technologies in an embodiment of the present application.

FIG. 2 is a schematic diagram of the effective spatial coverage of the combined positioning technology of BDS+5G and BDS+UWB in an embodiment of the present application.

FIG. 3 is a schematic diagram of an application environment in an embodiment of the present application.

FIG. 4 is a flowchart of a positioning method in an embodiment of the present application.

FIG. 5 is a schematic diagram of a time flow of a positioning method in an embodiment of the present application.

FIG. 6 is a flowchart of a positioning method in an embodiment of the present application.

FIG. 7 is a schematic diagram of a positioning method in an embodiment of the present application.

FIG. 8 is a schematic diagram of a time flow of a 5G and IMU time registration method in an embodiment of the present application.

FIG. 9 is a flowchart of a step of estimating a second 5G output value in an embodiment of the present application.

FIG. 10 is a flowchart of the steps of training a neural network in an embodiment of the present application.

FIG. 11 is a flowchart of a step of determining positioning information of a positioning device in an embodiment of the present application.

FIG. 12 is a schematic block diagram of a positioning apparatus in an embodiment of the present application.

FIG. 13 is a schematic structural diagram of a positioning device in an embodiment of the present application.

FIG. 14 is a schematic structural diagram of a positioning system in an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

In order to achieve continuous high-precision positioning in space, the space can be divided according to the characteristics and limitations of the positioning method, that is, from the countryside to the city, from the outdoor to the indoor, as shown in Figure 1, where the effective coverage of the space refers to the available space. The proportion of the spatial area for high-precision positioning. Satellite navigation systems, taking BeiDou Navigation Satellite System (BDS) as an example, can only perform high-precision positioning in outdoor open areas, including rural and suburban areas. Due to the high-rise buildings in the city, on the one hand, it will block satellite signals, and on the other hand On the one hand, the multipath effect is serious, so its positioning accuracy and effective spatial coverage are greatly reduced. In addition, UWB can only perform indoor high-precision positioning. According to Figure 1, it can be seen that the positioning space of BDS and UWB does not have strong complementarity. Therefore, , as shown in Figure 2, the combination of BDS and UWB cannot achieve the continuity and effectiveness of positioning in space, that is, it cannot achieve space-time universal high-precision positioning.

The fifth-generation mobile communication technology (5th-Generation, 5G) positioning is an emerging positioning technology. It can achieve decimeter-level or even centimeter-level positioning accuracy when 5G base stations are densely deployed. Compared with UWB, 5G positioning requires no additional labor. and equipment cost, and more importantly, its effective spatial coverage is much higher than that of UWB, forming a strong spatial complementarity with BDS. As can be seen from Figure 1, from rural to indoor, the effective spatial coverage of BDS gradually decreases, while 5G The effective coverage rate of space increases gradually, and the two have a strong complementary relationship in space, so the deep fusion of the two can achieve the continuity of positioning in space. As shown in Figure 2, BDS positioning is the main 5G positioning in the range from the countryside to the suburbs, and 5G positioning is the main BDS positioning in the urban to indoor range. In addition, due to the occlusion of buildings, vehicles and trees, etc. , BDS+5G is difficult to achieve continuous high-precision positioning in time. Therefore, in this application, Inertial Measurement Unit (IMU) is further combined to achieve continuous high-precision positioning in time, that is, BDS+5G and IMU. Complementary in time.

Therefore, in the positioning methods provided by the following embodiments of this application, the satellite navigation system, 5G and IMU are deeply integrated to form complementary advantages, thereby effectively improving the continuity and effectiveness of positioning in time and space, that is, to achieve Space-time pervasive high-precision positioning.

The positioning method provided by the present application can be applied in the application environment as shown in FIG. 3 . The application environment includes a positioning device 301 , a satellite navigation system 302 and a 5G base station 303 . The positioning device 301 is connected in communication with the satellite navigation system 302 and the 5G base station 303, respectively. The satellite navigation system 302 may include multiple satellites, the positioning device 301 may be configured with a satellite positioning module, a 5G module and an IMU, the satellite positioning module may include a receiver, and the positioning device 301 may receive one or more of the satellite navigation system 302 through the receiver. The positioning device 302 can also receive the second measurement signal of the 5G base station 303 through the 5G module. In addition, the positioning device 302 can also read the IMU output of the positioning device 302 such as the position, speed, and attitude output by the IMU. value. The positioning device 301 executes the positioning method of any embodiment of the present application, thereby determining the positioning information such as the position, speed, and attitude of the positioning device 302 itself, so as to realize precise positioning of itself.

In one embodiment, referring to FIG. 4 and FIG. 5 , a positioning method is provided. Taking the positioning method applied to the positioning device 301 shown in FIG. 3 as an example, it may include:

Step S402, acquiring the time to be positioned.

The time to be positioned refers to the time at which the positioning information of the positioning device corresponding to the time needs to be determined. The time to be positioned may be determined according to the positioning requirements of the positioning device. In this step, the positioning device determines the moment to be positioned that currently needs to be positioned.

Step S404, acquiring the IMU output value of the IMU loaded on the positioning device at the moment to be located.

The positioning device refers to a device that needs to be positioned. The positioning device may be a device that executes the positioning method of the present application, so that the positioning device may determine its own positioning information by executing the positioning method of the present application.

The positioning device is loaded with an IMU, and the IMU may include sensors such as an accelerometer and a gyroscope. Referring to FIG. 5 , which is a schematic diagram of a positioning method according to an embodiment of the present application, wherein T _I1 , T _I2 , _{T I3} , . Each IMU sampling time T _In outputs the mechanically programmed IMU output value. The IMU output value may include raw data directly measured by the IMU and/or data calculated based on these raw data, for example, may include the acceleration, position, velocity and attitude ( Attitude includes heading angle, pitch angle and roll angle) and so on. The position output by the IMU can be calculated according to its initial position (known)/the position at the last moment combined with the raw data measured at the current moment.

Step S406, when the first measurement signal from the 5G base station is received within the first predetermined time interval around the time to be positioned, determine the positioning information of the positioning device based on the IMU output value and the first measurement signal.

Wherein, the first predetermined time interval around the moment to be positioned may be determined according to the actual situation, for example, may be determined according to the required number of first measurement signals. In this step, one or more first measurement signals may need to be received within the first predetermined time interval. Taking the need to receive three consecutive first measurement signals of three consecutive 5G sampling moments within the first predetermined time interval as an example, in this embodiment, the nearest 5G measurement moment after the moment to be positioned and the 5G measurement moment can be taken. The maximum possible time interval in which the previous two 5G measurement moments are located is used as the first predetermined time interval. For example, if the IMU sampling interval is sampling every 1 ms, the 5G sampling interval is sampling every 9 ms, and the time to be positioned is the 35 ms, then The first predetermined time interval may be set to (8ms, 44ms).

The first measurement signal of the 5G base station is a signal used to locate the positioning device obtained by the 5G base station observing the positioning device. The 5G base station observes the positioning device within its observation range at the 5G sampling interval to obtain a first measurement signal and sends it to the positioning device.

The positioning information is information representing the positioning result of the positioning device, and the positioning information may include, for example, the position, speed, and attitude of the positioning device.

In this step, if the positioning device receives the first measurement signal from the 5G base station in the first predetermined time interval around the time to be positioned, it means that the current state of the first measurement signal from the 5G base station is good, and the first measurement signal can be used. The measurement signal is combined with the output value of the IMU to accurately obtain the positioning information at the moment to be positioned. As shown in FIG. 5 , for example, if the first measurement signal or estimated value of the _5G base station is delivered to the positioning device at time TB, the positioning device is positioned using the first measurement signal and the output value of the IMU.

Step S408, when the second measurement signal from the navigation satellite is received within the second predetermined time interval around the time to be positioned, determine the positioning information of the positioning device based on the IMU output value and the second measurement signal.

The setting of the second predetermined time interval around the moment to be located in step S408 may be the same as the setting of the first predetermined time interval around the moment to be located in step S406, and the second predetermined time interval may be the same as the first predetermined time interval. The intervals are the same or different. For example, the second predetermined time interval may be determined according to the number of the second measurement signals to be received in the second predetermined time interval, and the specific details will not be repeated here.

Navigation satellites refer to one or more navigation satellites in a navigation satellite system, for example, a navigation satellite system may be a Global Navigation Satellite System (GNSS), for example, a navigation satellite system may include a BeiDou Navigation Satellite System (BeiDou Navigation Satellite System). , BDS), Global Positioning System (Global Positioning System, GPS), Galileo Navigation Satellite System (Galileo Navigation Satellite System, Galileo) and/or GLONASS Satellite Navigation System (Global Orbiting Navigation Satellite System, GLONASS) etc.

The second measurement signal of the navigation satellite is a signal obtained by the navigation satellite observing the positioning device and used for positioning the positioning device. The navigation satellite observes the positioning device at the satellite sampling time to obtain a second measurement signal and sends it to the positioning device.

In this step, if the positioning device receives the second measurement signal from the navigation satellite in the second predetermined time interval around the time to be positioned, it means that the current state of the second measurement signal from the navigation satellite is good, then the second measurement signal can be used. The measurement signal is combined with the output value of the IMU to accurately obtain the positioning information at the moment to be positioned. As shown in FIG. 5 , for example, if the second measurement signal of the navigation satellite is delivered to the positioning device at time _TG , the positioning device is positioned using the second measurement signal and the output value of the IMU.

The above positioning method, combined with 5G and IMU tightly coupled positioning and satellite navigation system and IMU tightly coupled positioning, when receiving the first measurement signal from the 5G base station in the first predetermined time interval around the moment to be positioned, combined with the first measurement signal and the output value of the IMU to determine the positioning information of the positioning device, and at the same time when the second measurement signal from the navigation satellite is received in the second predetermined time interval around the time to be positioned, the second measurement signal and the output value of the IMU are combined to determine the positioning device. Since 5G positioning and satellite positioning have good complementarity in indoor and outdoor environments, the positioning method of the present application that deeply integrates the satellite navigation system, 5G and IMU can effectively improve positioning in time and space. Continuity and effectiveness.

The 5G and IMU tightly coupled positioning method involved in step S406 will be described in detail below.

Since the sampling times of the 5G base station and the IMU are often different, there is generally a time difference between the 5G sampling time of the first measurement signal obtained in the above step S406 and the IMU sampling time of the IMU output value, so it is necessary to solve the high precision between the two. The time-to-time registration problem, that is, the output values of the 5G base station and the IMU at the same time need to be estimated for positioning.

In one embodiment, as shown in FIG. 6 and FIG. 7 , the time to be located in the above step S402 is the IMU sampling time of the IMU loaded on the positioning device, and the first measurement signal in the above step S406 may include the first 5G output value and the base station position of the 5G base station, in step S406, when the first measurement signal from the 5G base station is received within the first predetermined time interval around the time to be positioned, based on the IMU output value and the first measurement signal, determine the location of the positioning device. Location information can include:

Step S602, when the first measurement signal from the 5G base station is received within the first predetermined time interval around the time to be located, the first measurement signal includes the first 5G output value and the base station position of the 5G base station, based on the first 5G output value. , estimating the second 5G output value of the 5G base station at the moment to be located; and

Step S604, based on the IMU output value and the base station location, calculate the third 5G output value of the IMU at the time to be positioned, and determine the positioning information of the positioning device in combination with the second 5G output value and the third 5G output value.

In this embodiment, the time to be located is set to belong to the sampling time of the IMU, and the sampling time of the IMU shall prevail. By estimating the second 5G output value of the 5G base station at the time to be located, the IMU is calculated based on the output value of the IMU and the position of the base station. The third 5G output value at the to-be-located moment, so that the third 5G output value of the IMU and the second 5G output value of the 5G base station at the same to-be-located moment and having the same form can be easily and quickly determined, so as to facilitate the subsequent combination of the IMU Perform positioning calculation with the data of 5G base station.

Wherein, the first 5G output value, the second 5G output value and the third 5G output value in the above steps S602 and S604 refer to data having the same format as the data output by the 5G base station for positioning. In one embodiment, the first 5G output value, the second 5G output value and the third 5G output value may each include an angle of arrival (Angle of Arrival, AoA) and a time of arrival (Time Of Arrival, TOA).

其中

分别为装载IMU的定位设备在5G基站本地球坐标系下的径向距离、方位角和俯仰角值。T _Bn表示5G基站输出测量值或者估计值的5G采样时刻，相应的第一5G输出值表示为

其中

分别为装载5G模块的定位设备在5G基站本地球坐标系下的径向距离、方位角和俯仰角值，其中

和

为5G基站获取的AOA信息，

为5G基站获取的TOA信息，c为光速。当5G基站在待定位的T _I19时刻(即图3中虚线框内的时刻)周围第一预定时间区间内的第3个输出值B _I3下发到定位设备时，需要估计出T _I19时刻的5G基站的第二5G输出值，以便后续对T _I19时刻的IMU的第三5G输出值和5G基站的第二5G输出值进行融合计算。 As shown in Figure 8, where T _In represents the nth IMU sampling time of the IMU output mechanical arrangement value, and the third 5G output value of the corresponding IMU at the time to be positioned can be expressed as

in

are the radial distance, azimuth and elevation values of the positioning device loaded with the IMU in the local earth coordinate system of the 5G base station. T _Bn represents the 5G sampling time when the 5G base station outputs the measured value or estimated value, and the corresponding first 5G output value is expressed as

in

are the radial distance, azimuth and elevation values of the positioning device loaded with the 5G module in the local earth coordinate system of the 5G base station, where

and

The AOA information obtained for the 5G base station,

is the TOA information obtained by the 5G base station, and c is the speed of light. When the 5G base station sends the third output value B _I3 in the first predetermined time interval around the to-be-located time T _I19 (that is, the time in the dashed box in Figure 3 ) to the positioning device, it is necessary to estimate the time at T _I19 . The second 5G output value of the 5G base station, so that the third 5G output value of the IMU at the time of T _I19 and the second 5G output value of the 5G base station can be subsequently merged and calculated.

In one embodiment, the above-mentioned first 5G output value may include: at M 5G sampling moments of the 5G base station within the first predetermined time interval, M first 5G outputs of the uplink reference signal of the positioning device measured by the 5G base station value, M is a positive integer.

The value of M can be determined according to actual requirements, and in this embodiment of the present application, M≧2 can be taken. For example, M can take 3. In other embodiments, M may take on more or less values.

According to different values of M, different methods may be used to estimate the second 5G output value of the 5G base station at the moment to be positioned. For example, when M=1, that is, when there is only one first 5G output value, an extrapolation method can be used to estimate the corresponding second 5G output value, and the extrapolation method can be any existing extrapolation estimation method.

In one embodiment, when M≥2, the time registration method between the 5G and the IMU involved in step S602 is to estimate, based on the first 5G output value, the difference between the second 5G output value of the 5G base station at the moment to be positioned The steps may include: using an interpolation method to estimate the second 5G output value of the 5G base station at the to-be-located time based on the M 5G sampling times, the M first 5G output values, and the to-be-located time.

According to different values of M, different interpolation methods may be used to estimate the second 5G output value. For example, when M=2, any existing interpolation method can be used to estimate the corresponding second 5G output value; and when M=3, for example, the corresponding Lagrangian three-point interpolation method can be used to estimate the corresponding second 5G output value. Second 5G output value, and so on.

Taking M=3 as an example, for example, as shown in FIG. 8 , according to the three consecutive first 5G output values B _I1 , B _I2 , B _I3 delivered to the positioning device within the first predetermined time interval around time T _I19 , the second 5G output value of the 5G base station at the time T _I19 can be estimated by the formula of the following Lagrangian three-point interpolation method:

In this embodiment, through the interpolation method, the second 5G output value at the to-be-located time can be estimated and obtained according to the first 5G output values at multiple known times around the to-be-located time.

Further, in addition to using the interpolation method to estimate the second 5G output value, the second 5G output value can also be estimated by further combining with a neural network.

In another embodiment, as shown in FIG. 9 , the step of estimating the second 5G output value of the 5G base station at the to-be-located moment based on the first 5G output value in step S602 may also include:

Step S902, at each to-be-located moment in the first time period after the positioning device is turned on, based on the M 5G sampling moments, the M first 5G output values, and the to-be-located moment, an interpolation method is used to estimate the 5G base station at the to-be-located moment. The second 5G output value.

时段)，采用拉格朗日三点插值法估算5G基站在待定位时刻的第二5G输出值，以图3中为例，

时段内的待定位的T _I19时刻的第二5G输出值同样可以通过式(1)计算。 Also taking M=3 as an example, in the initial stage of the positioning device executing the positioning method, that is, within the first time period after the positioning device is turned on (

period), the Lagrangian three-point interpolation method is used to estimate the second 5G output value of the 5G base station at the moment to be positioned. Taking Figure 3 as an example,

The second 5G output value at time T _I19 to be located within the time period can also be calculated by formula (1).

Step S904, in the first time period, based on the training set consisting of N 5G sampling moments in the first time period and N first 5G output values of N 5G sampling moments, train the neural network model, N ≥ 2; When the training is completed and the trained neural network model is obtained, enter the second time period.

时段，还同时运行基于神经网络的高精度时间配准方法。 While performing the interpolation method to estimate the second 5G output value in step S702, in this step S704, within the first time period, namely

Period, and also run a neural network-based high-precision temporal registration method.

时段，可以实时获取每相邻3个5G采样时刻以及该相邻3个5G采样时刻中首尾两个5G采样时刻的两个第一5G输出值作为LSTMNN的输入值，该相邻3个5G采样时刻中中间一个5G采样时刻对应的一个第一5G输出值作为对应的LSTMNN的输出值，获取多对这样的输入值-输出值以构成训练集，利用该训练集实时对LSTMNN进行训练。其中，输入值-输出值对的数目可以根据实际情况确定，例如可以是获取50对这样的输入值-输出值，或者更多或更少的输入值-输出值对。相应地N的取值可以根据输入值-输出值对的数目设定。以需要获取50对这样的输入值-输出值为例，相应的N可以例如取值为52，即获取连续的52个5G采样时刻的52个第一5G输出值，其中每相邻3个5G采样时刻和对应的3个第一5G输出值构成如上所述的一对输入值-输出值。相应地，在LSTMNN训练阶段，其在k时刻的输入矢量为[T _Bk-1,B _Ik-1,T _Bk+1,B _Ik+1,T _Bk] ^T，输出为B _Ik。 Taking the neural network using Long Short Term Memory Neural Network (LSTMNN) and M=3 as an example, in

During the period, the two first 5G output values of every three adjacent 5G sampling moments and the first and last two 5G sampling moments of the three adjacent 5G sampling moments can be obtained in real time as the input values of LSTMNN, and the three adjacent 5G sampling moments A first 5G output value corresponding to a 5G sampling time in the middle of the time is used as the output value of the corresponding LSTMNN, and multiple pairs of such input value-output value are obtained to form a training set, and the LSTMNN is trained in real time by using the training set. The number of input value-output value pairs may be determined according to actual conditions, for example, 50 such input value-output value pairs, or more or less input value-output value pairs may be obtained. Accordingly, the value of N can be set according to the number of input value-output value pairs. Taking the need to obtain 50 pairs of such input value-output value as an example, the corresponding N can be, for example, 52, that is to obtain 52 first 5G output values at 52 consecutive 5G sampling moments, of which every three adjacent 5G output values The sampling moment and the corresponding three first 5G output values constitute a pair of input value-output value as described above. Correspondingly, in the LSTMNN training stage, its input vector at time k is [T _Bk-1 , B _Ik-1 , T _Bk+1 , B _Ik+1 , T _Bk ] ^T , and the output is B _Ik .

处，LSTMNN已收敛，即可以获得训练后的神经网络模型，进入第二时间段。 LSTMNN adopts the online training mode, and the training algorithm adopts the training method based on Unscented Kalman Filter (UKF).

At this point, the LSTMNN has converged, that is, the trained neural network model can be obtained, and the second time period is entered.

Step S906, at each to-be-located moment in the second time period, input the to-be-located moment into the trained neural network model, and use the output value of the neural network model as the estimated second 5G output of the 5G base station at the to-be-located moment value.

之后，定位设备可以使用基于LSTMNN的高精度时间配准方法进行5G和IMU时间配准。 Also taking LSTMNN as an example, in this step, in the second time period, that is, the moment

After that, the positioning device can use the LSTMNN-based high-precision temporal registration method for 5G and IMU temporal registration.

When performing high-precision time registration, the input vector [T _Bk-1 , B _Ik-1 , T _Bk+1 , B _Ik+1 , T _Iα ] ^T at any time α to be positioned can be input to LSTMNN, that is, we can get The output value is B _Iα , where T _Bk-1 ≤ T _Iα ≤ T _Bk+1 , and the output value B _Iα is the second 5G output value of the 5G base station at time α to be positioned.

Compared with the interpolation estimation method, the neural network has higher estimation accuracy, but the neural network needs a certain training time. In this embodiment, at the initial stage of positioning by the positioning device, the interpolation method is used to estimate the second 5G output value at the moment to be positioned, and at the same time, at the initial stage of positioning by the positioning device, the neural network is trained synchronously until the neural network training is completed. Then, the neural network is used to estimate the second 5G output value at the moment to be positioned, which can improve the accuracy of positioning time allocation preparation while taking into account the overall time utilization efficiency.

In one embodiment, as shown in FIG. 10 , the training of the neural network based on the training set in step S904 includes:

Step S1002: Initialize adjustable parameters of the neural network model, where the adjustable parameters include weights and bias values of the neural network model.

The neural network model may have a set number of hidden layers and the number of nodes of each layer of the input layer, the hidden layer and the output layer. When training the neural network model, the adjustable parameters of the neural network can be initialized, including the bias value of each layer and the weight of the edge, etc., to initially obtain the initialized neural network model.

Step S1004, establishing a state space model about the adjustable parameters of the neural network model.

Taking LSTMNN as an example, in order to use the UKF algorithm to train LSTMNN, the state space model of the adjustable parameters of LSTMNN should be established first. By leveraging this state-space model, the UKF algorithm can recursively estimate tunable parameters in the LSTMNN. The state space model for the tunable parameters of LSTMNN is:

θ(k)=θ(k-1)+w(k-1)

y(k)=h[θ(k),u(k)]+v(k) (2)

Where θ(k) is the set vector of LSTMNN adjustable parameters at time k, that is, the weight matrix and bias vector of LSTMNN, u(k)=[T _Bk-1 , B _Ik-1 , T _Bk+1 , B _Ik+1 ,T _Bk ] ^T and y(k)=B _Ik are the input vector and output value of LSTMNN respectively, h[ ] represents the internal dynamic process of LSTMNN, w(k-1) and v(k) are the state and Observe the noise vector. By using the state space model shown in equation (2), the UKF algorithm can recursively estimate the tunable parameters in the LSTMNN.

Step S1006, based on the state space model and the training set, use the UKF algorithm to recursively estimate the adjustable parameters, until the output error of the neural network model reaches a predetermined error range, to determine the adjustable parameters after training; And

In this step, the state space model shown in formula (2) can be used to substitute each pair of input and output values in the training set into the LSTMNN for recursive estimation until the output error of the LSTMNN reaches the predetermined error range, that is, the LSTMNN converges, The adjustable parameters at this time are the adjustable parameters after training.

Step S1008, generating a trained neural network model based on the adjustable parameters after training.

In this step, the trained neural network model is correspondingly determined by using the adjustable parameters after training.

In this embodiment, by using the UKF method to train the neural network, the second-order derivative information can be used, the convergence speed is fast, and it is not easy to fall into a local minimum value. Therefore, the time registration accuracy of the neural network model obtained by the final training is The accuracy of estimating the second 5G output value is high.

The neural network of this application is described above by taking LSTMNN as an example. As a recurrent neural network, LSTMNN can effectively improve the accuracy of time registration when applied to the time registration method provided by this application, but the neural network of this application does not limited to this. For example, the neural network of the present application can also use a multi-layer perceptron (Multi-Layer Perceptron, MLP), and the UKF algorithm can also be used to train the MLP, and for example, the neural network of the present application can also be selected (Radial Basis Function, RBF) neural network and so on.

In one embodiment, as shown in FIG. 11 , in step S604, based on the IMU output value and the base station location, the third 5G output value of the IMU at the time to be located is calculated, and the second 5G output value and the third 5G output value are determined to determine The positioning information of the positioning device includes:

Step S1102, based on the IMU output value and the base station location, calculate the third 5G output value of the IMU at the moment to be positioned.

In the foregoing step S404, the obtained IMU output value may include the acceleration, position, speed, and attitude of the positioning device. Specifically, the position may include the latitude, longitude and altitude of the positioning device in the ground-fixed coordinate system, the speed may include the easting speed, the northing speed and the sky speed of the positioning device in the navigation coordinate system, and the attitude may include the positioning device in the carrier coordinate system. The heading, pitch, and roll angles relative to the navigation coordinate system.

In this step, the positioning device can calculate the third 5G output value of the IMU at the moment to be positioned based on the above-mentioned IMU output value and the base station location, and the third 5G output value can be expressed as

Step S1104 , based on the positioning information of the positioning device calculated at the previous positioning time and the IMU output value at the previous positioning time, construct the error state equation of the 5G and the IMU at the time to be positioned.

For example, the positioning device can construct the 5G and IMU error state equations at the current to-be-located moment as shown in equations (3)-(5), where the IMU uses a three-axis accelerometer and a three-axis gyroscope.

为失准角的一阶微分，δv ⁿ为导航坐标系下的速度误差矢量，

为速度误差矢量的一阶微分，δp＝[δL δλ δh] ^T为地固坐标系下的位置误差矢量，分别为地固坐标系下的纬度误差、经度误差和高度误差，

为位置误差矢量的一阶微分，ε ^b为陀螺仪零漂误差矢量，

为加速度计零漂误差矢量，定义导航坐标系为“东—北—天”地理坐标系，

为载体坐标系到导航坐标系的坐标变换矩阵。 where φ is the misalignment angle of the calculated navigation coordinate system relative to the ideal navigation coordinate system,

is the first-order differential of the misalignment angle, δv ⁿ is the velocity error vector in the navigation coordinate system,

is the first-order differential of the velocity error vector, δp=[δL δλ δh] ^T is the position error vector under the ground-fixed coordinate system, which are the latitude error, longitude error and altitude error under the ground-fixed coordinate system, respectively,

is the first-order differential of the position error vector, ^εb is the zero-drift error vector of the gyroscope,

is the zero-drift error vector of the accelerometer, and defines the navigation coordinate system as the "east-north-sky" geographic coordinate system,

It is the coordinate transformation matrix from the carrier coordinate system to the navigation coordinate system.

In the above formulas (3)-(5):

M _ap =M ₁ +M ₂ (11)

M _vp =(v ⁿ ×)(2M ₁ +M ₂ )+M ₃ (14)

为在前一已定位时刻在IMU中的加速度计的测量值。 where v ⁿ =[v _E v _N v _U ] ^T are respectively the easting speed, northing speed and sky speed under the navigation coordinate system obtained by the positioning device at the previous positioning moment, p=[L λ h ] are respectively the latitude, longitude and altitude in the ground-fixed coordinate system obtained by the positioning device at the previous positioning moment. ω _ie is the angular rate of the earth's rotation, R _M is the main radius of curvature of the meridian circle, R _N is the main radius of curvature of the 卯unitary circle, g _e is the equatorial gravity, g _p is the pole gravity, R _e is the equatorial radius, and f is usually taken as 1/ 298.257223563, β ₂ usually takes 3.08×10 ^-6 s ^-2 , β ₃ usually takes 8.08×10 ^-9 s ^-2 ,

is the measurement of the accelerometer in the IMU at the previous positioned instant.

The 5G and IMU error state equations are used to model the evolution of the IMU's mechanical arrangement value and the true value error. The input value is the estimated value output by the Error State Kalman Filter (ESKF) at the previous moment, that is, the state error. The estimated value, the output value is the predicted value of the state error at the next moment, and the output value acts on [δL δλ δh] in the error observation equation. The 5G and IMU error state equations are used to predict the state error at the next moment.

Step S1106, based on the second 5G output value and the third 5G output value at the to-be-located time, construct an error observation equation of the 5G and the IMU at the to-be-located time.

In this step, the positioning device can construct the 5G and IMU error observation equations at the current to-be-located moment as shown in the following formula (24).

In the above formula (24):

为装载有IMU的定位设备在5G基站本地笛卡尔坐标系下的坐标值，w _B为5G基站的观测噪声矢量，

为地固坐标系到5G基站本地坐标系的坐标变换矩阵，

in

is the coordinate value of the positioning device loaded with the IMU in the local Cartesian coordinate system of the 5G base station, w _B is the observation noise vector of the 5G base station,

is the coordinate transformation matrix from the ground-fixed coordinate system to the local coordinate system of the 5G base station,

Step S1108, the error state equations of the 5G and the IMU and the error observation equations of the 5G and the IMU are simultaneously combined, and the ESKF method is used to iteratively estimate the positioning information of the positioning device to determine the positioning information of the positioning device.

In this step, the positioning device can correct the state error predicted value output by the error state equation through the simultaneous equations (3)-(5) and (24), using the error observation equation and ESKF to obtain the final estimated state error value , the input value is the 5G observation value and the IMU mechanical arrangement value, and the output value is the state error estimate value. The IMU mechanical arrangement value minus the state error estimate value is the final state estimate value of the positioning device (ie position, speed and attitude), thus By using the error state equation in equations (3)-(5), the error observation equation in equation (24) and the ESKF, the state error can be estimated recursively, and the iteration of the position, velocity and attitude of the positioning device at the current moment to be positioned is performed. estimation to determine the positioning information of the positioning device at the current to-be-located moment. The positioning information may include the position, velocity and attitude of the positioning device.

The 5G and IMU tightly coupled positioning method involved in step S406 has been described in detail above, and the following will continue to describe the satellite navigation system and IMU tightly coupled positioning method involved in step S408 in detail. Many of the details described below for the satellite navigation system and IMU tightly coupled positioning method are similar to the above 5G and IMU tightly coupled positioning method, for example, the above time registration method for 5G and IMU can be used in the same way for satellite navigation system. In the temporal registration method with the IMU, the similar implementation details and beneficial effects can be found in the above description of the 5G and IMU tightly coupled positioning method.

In one embodiment, as shown in FIG. 6 , the time to be located in the above step S402 is the IMU sampling time of the IMU loaded on the positioning device, and the second measurement signal in the above step S408 may include the first satellite output value and the navigation The satellite position of the satellite, in step S408, when the second measurement signal from the navigation satellite is received in the second predetermined time interval around the time to be positioned, based on the IMU output value and the second measurement signal, it is determined that the positioning information of the positioning device can be include:

Step S606, when the second measurement signal from the navigation satellite is received within the second predetermined time interval around the time to be positioned, the second measurement signal includes the first satellite output value and the satellite position of the navigation satellite, based on the first satellite output value. , estimating the second satellite output value of the navigation satellite at the moment to be positioned; and

Step S608: Calculate the third satellite output value of the IMU at the time to be positioned based on the IMU output value and the satellite position, and determine the positioning information of the positioning device in combination with the second satellite output value and the third satellite output value.

In this embodiment, the time to be positioned is set to belong to the sampling time of the IMU, and the sampling time of the IMU shall prevail. By estimating the second satellite output value of the navigation satellite at the time to be positioned, the IMU is calculated based on the output value of the IMU and the satellite position. The third satellite output value at the to-be-positioned moment, so that the third satellite output value of the IMU and the second satellite output value of the navigation satellite at the same to-be-positioned moment and having the same form can be easily and quickly determined, so as to facilitate the subsequent combination of the IMU and navigation satellite data for positioning solution.

Wherein, the first satellite output value, the second satellite output value and the third satellite output value in the above steps S606 and S608 refer to data having the same form as the data output by the navigation satellite for positioning. In one embodiment, the first satellite output value, the second satellite output value, and the third satellite output value each include pseudoranges and pseudorange rates.

In one embodiment, the above-mentioned first satellite output values include: X satellite sampling times of the navigation satellite within the second predetermined time interval, X first satellite output values of the positioning device observed by the navigation satellite, and X is positive Integer.

The value of X can be determined according to actual requirements, and in this embodiment of the present application, X≧2 can be taken. For example, X can take 3. In other embodiments, X may take on more or less values.

According to different values of X, different methods can be used to estimate the second satellite output value of the navigation satellite at the moment to be positioned. For specific examples of different estimation methods used when X takes different values, refer to the above-mentioned specific example of estimating the second 5G output value of the 5G base station at the time to be positioned when M takes different values, which will not be repeated here.

In one embodiment, the time registration method between the satellite and the IMU involved in step S606, that is, based on the first satellite output value, the step of estimating the second satellite output value of the navigation satellite at the moment to be positioned may include: based on X The second satellite output value of the navigation satellite at the to-be-positioned time is estimated by interpolation method.

For a specific example and beneficial effects of using the interpolation method to estimate the second satellite output value of the navigation satellite at the time to be positioned, please refer to the above-mentioned estimation of the second 5G output value of the 5G base station at the time to be positioned by using the interpolation method The specific examples and beneficial effects of this method will not be repeated here.

In another embodiment, based on the first satellite output value in step S606, estimating the second satellite output value of the navigation satellite at the moment to be positioned includes:

At each to-be-located moment in the first time period after the positioning device is turned on, based on the X satellite sampling moments, the X first satellite output values, and the to-be-located moment, an interpolation method is used to estimate the second time of the navigation satellite at the to-be-located moment. satellite output value;

In the first time period, the neural network model is trained based on the Y satellite sampling moments in the first time period and the Y first satellite output values of the Y satellite sampling moments in the training set, Y≥2; When the training is completed and the trained neural network model is obtained, enter the second time period;

At each to-be-positioned moment in the second time period, the to-be-positioned moment is input into the trained neural network model, and the output value of the neural network model is used as the estimated second satellite output value of the navigation satellite at the to-be-positioned moment.

In this embodiment, the interpolation method combined with the neural network model is used to estimate the second satellite output value of the navigation satellite at the time to be positioned. Specific examples and beneficial effects of the estimation of the second 5G output value of the base station at the moment to be positioned will not be repeated here.

In one embodiment, the above-mentioned training of the neural network based on the training set includes:

Initialize the adjustable parameters of the neural network model, and the adjustable parameters include the weights and bias values of the neural network model;

Establish a state space model of the adjustable parameters of the neural network model;

Based on the state space model and the training set, the UKF algorithm is used to recursively estimate the adjustable parameters until the output error of the neural network model reaches a predetermined error range, so as to determine the adjustable parameters after training; and

Based on the tunable parameters after training, a trained neural network model is generated.

For specific examples and beneficial effects of training the neural network model in this embodiment, reference may be made to the specific examples and beneficial effects of training the neural network model in steps S1002-S1008 of the above-mentioned 5G and IMU tightly coupled positioning method, which will not be repeated here. Repeat.

In the above-mentioned satellite navigation system and IMU tightly coupled positioning method of the present application, the specific implementation details such as the calculation formula in step S608 can be implemented by using any existing satellite navigation system and IMU combined positioning method. For example, reference [1] Titterton D H, Weston J L. Strapdown inertial navigation technology [M]. 2004. and reference [2] Noureldin A, Karamat T B, George J. Fundamentals of Inertial Navigation, Satellite-based The satellite navigation system and the IMU combined positioning method disclosed in Positioning and their Integration [M]. 2013. The disclosures of these references are incorporated herein by reference.

In the positioning method of the present application, when the first measurement signal from the 5G base station is received within the first predetermined time interval around the moment to be positioned, and the first measurement signal from the 5G base station is also received within the first predetermined time interval around the moment to be positioned During the first measurement of the signal, the positioning device can select one of the steps S406 and S408 to execute, so as to use one of the 5G and IMU tightly coupled positioning methods and the satellite navigation system and one of the IMU tightly coupled positioning methods to position the positioning device, Alternatively, the positioning device may also combine the 5G and IMU tightly coupled positioning method and both the satellite navigation system and the IMU tightly coupled positioning method to position the positioning device.

In one embodiment, the positioning method of the present application may further include:

When the first measurement signal from the 5G base station is received within the first predetermined time interval around the moment to be positioned, and the first measurement signal from the 5G base station is also received within the first predetermined time interval around the moment to be positioned, based on the IMU The output value and the first measurement signal are used to determine the positioning information of the positioning device; based on the positioning information and the second measurement signal, the final positioning information of the positioning device is determined.

Further, in one embodiment, the first measurement signal includes the first 5G output value and the base station position of the 5G base station, the second measurement signal includes the first satellite output value and the satellite position of the navigation satellite, and the above positioning method may include:

When the first measurement signal from the 5G base station is received within the first predetermined time interval around the moment to be positioned, and the first measurement signal from the 5G base station is also received within the first predetermined time interval around the moment to be positioned, based on the A 5G output value, estimate the second 5G output value of the 5G base station at the moment to be positioned; based on the IMU output value and the base station location, calculate the third 5G output value of the IMU at the moment to be positioned, combined with the second 5G output value and the third 5G output value The output value determines the positioning information of the positioning device; based on the first satellite output value, the second satellite output value of the navigation satellite at the time to be positioned is estimated; The fourth satellite output value at the bit moment; the final positioning information of the positioning device is determined in combination with the second satellite output value and the fourth satellite output value.

Alternatively, in another embodiment, the positioning method of the present application may further include:

When the first measurement signal from the 5G base station is received within the first predetermined time interval around the moment to be positioned, and the first measurement signal from the 5G base station is also received within the first predetermined time interval around the moment to be positioned, based on the IMU The output value and the second measurement signal are used to determine the positioning information of the positioning device; based on the positioning information and the first measurement signal, the final positioning information of the positioning device is determined.

Further, in one embodiment, the first measurement signal includes the first 5G output value and the base station position of the 5G base station, the second measurement signal includes the first satellite output value and the satellite position of the navigation satellite, and the above positioning method may include:

When the first measurement signal from the 5G base station is received within the first predetermined time interval around the moment to be positioned, and the first measurement signal from the 5G base station is also received within the first predetermined time interval around the moment to be positioned, based on the A satellite output value to estimate the second satellite output value of the navigation satellite at the moment to be positioned; based on the IMU output value and the satellite position, calculate the third satellite output value of the IMU at the moment to be positioned, combining the second satellite output value and the third satellite output value The output value determines the positioning information of the positioning device; based on the first 5G output value, the second 5G output value of the 5G base station at the time to be positioned is estimated; based on the determined positioning information and the base station position, the satellite navigation system and the IMU tightly coupled subsystem are calculated At the fourth 5G output value at the moment to be positioned, the positioning information of the positioning device is determined in combination with the second 5G output value and the fourth 5G output value.

The technical solutions of the above two embodiments combine both the 5G and IMU tightly coupled positioning methods, as well as the satellite navigation system and the IMU tightly coupled positioning method to locate the positioning device, and the corresponding calculation formulas and other details and beneficial effects can be referred to The above descriptions of the 5G and IMU tightly coupled positioning method and the satellite navigation system and the IMU tightly coupled positioning method will not be repeated here.

In the above two embodiments, when the first measurement signal from the 5G base station is received within the first predetermined time interval around the moment to be positioned, and the first measurement signal from the 5G base station is also received within the first predetermined time interval around the moment to be positioned During the first measurement of the signal, the positioning device uses both the 5G and IMU tightly coupled positioning method and the satellite navigation system and the IMU tightly coupled positioning method to locate the positioning device, thereby further improving the positioning accuracy.

It should be understood that although the various steps in the flowcharts of FIGS. 4 , 6 and 9-11 are shown in sequence as indicated by arrows, these steps are not necessarily executed sequentially in the sequence indicated by arrows. Unless explicitly stated herein, the execution of these steps is not strictly limited to the order, and these steps may be performed in other orders. Moreover, at least a part of the steps in FIGS. 4, 6 and 9-11 may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but may be executed at different times The execution order of these sub-steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least a part of sub-steps or stages of other steps.

In one embodiment, referring to FIG. 12 , a positioning apparatus 1200 is also provided, including: a time obtaining module 1201 , an IMU value obtaining module 1202 , a first positioning module 1203 , and a second positioning module 1204 .

The time obtaining module 1201 is used to obtain the time to be located.

The IMU value acquisition module 1202 is configured to acquire the IMU output value of the IMU at the time to be located.

The first positioning module 1203 is configured to determine the positioning information of the positioning device based on the IMU output value and the first measurement signal when the first measurement signal from the 5G base station is received within the first predetermined time interval around the time to be positioned.

The second positioning module 1204 is configured to determine the positioning information of the positioning device based on the IMU output value and the second measurement signal when receiving the second measurement signal from the navigation satellite within the second predetermined time interval around the time to be positioned.

The positioning device of this embodiment, combining 5G and IMU tightly coupled positioning and satellite navigation system and IMU tightly coupled positioning, when receiving the first measurement signal from the 5G base station in the first predetermined time interval around the moment to be positioned, combined with the first measurement signal from the 5G base station. a measurement signal and an IMU output value to determine the positioning information of the positioning device, and at the same time when a second measurement signal from the navigation satellite is received in a second predetermined time interval around the time to be positioned, the second measurement signal and the IMU output value are combined to obtain To determine the positioning information of the positioning device, since 5G positioning and satellite positioning have good complementarity in indoor and outdoor environments, the positioning method of the present application that deeply integrates the satellite navigation system, 5G and IMU can effectively improve the positioning time and time. Spatial continuity and validity.

In one embodiment, referring to FIG. 13, a positioning device 1300 is also provided, including an IMU module 1301, a 5G module 1302, a satellite positioning module 1303, a memory 1304 and a processor 1305, the IMU module 1301, the 5G module 1302, the satellite positioning module The module 1303 and the memory 1304 are respectively connected with the processor 1305;

The IMU module 1301 obtains the IMU output value of the positioning device at the IMU sampling time, and outputs the IMU output value to the processor 1305;

The 5G module 1302 receives the first measurement signal of the uplink reference signal of the positioning device measured by the 5G base station at the 5G sampling time from the 5G base station, and outputs the first measurement signal to the processor 1305;

The satellite positioning module 1303 receives the second measurement signal of the positioning device observed by the navigation satellite at the satellite sampling time from the navigation satellite, and outputs the second measurement signal to the processor 1305;

The memory 1304 stores computer programs; and

When the processor 1305 executes the computer program, the following methods are implemented:

Obtain the time to be positioned, where the time to be positioned is the IMU sampling time of the IMU loaded on the positioning device;

Obtain the IMU output value of the IMU at the moment to be positioned;

When receiving the first measurement signal from the 5G base station within the first predetermined time interval around the time to be positioned, determining the positioning information of the positioning device based on the IMU output value and the first measurement signal;

When the second measurement signal from the navigation satellite is received within the second predetermined time interval around the time to be positioned, the positioning information of the positioning device is determined based on the IMU output value and the second measurement signal.

In other embodiments, the processor 1305 in the above-mentioned positioning device 1300 also implements the positioning method of any one of the above-mentioned embodiments when executing the computer program.

In one embodiment, the positioning device 1300 may be any one of a mobile phone, a tablet computer, a portable wearable device, a vehicle, and a ship. In other embodiments, the positioning device 1300 may also be a component mounted on a mobile phone, a tablet computer, a portable wearable device, a vehicle, or a ship.

In one embodiment, referring to FIG. 14 , a positioning system 1400 is also provided, including a 5G base station 1401, a navigation satellite 1402 and a positioning device 1300, and the positioning device 1300 is respectively connected in communication with the 5G base station 1401 and the navigation satellite 1402;

The 5G base station 1401 measures the first measurement signal of the uplink reference signal of the positioning device at the 5G sampling time, and sends the first measurement signal to the positioning device;

The navigation satellite 1402 observes the second measurement signal of the positioning device at the satellite sampling time, and outputs the second measurement signal to the positioning device;

The positioning device 1300 performs the following methods:

Get the time to be positioned;

Obtain the IMU output value of the IMU at the moment to be positioned;

When receiving the first measurement signal from the 5G base station within the first predetermined time interval around the time to be positioned, determining the positioning information of the positioning device based on the IMU output value and the first measurement signal;

When the second measurement signal from the navigation satellite is received within the second predetermined time interval around the time to be positioned, the positioning information of the positioning device is determined based on the IMU output value and the second measurement signal.

In other embodiments, the above-mentioned positioning device 1300 also implements the positioning method of any one of the above-mentioned embodiments.

In one embodiment, a computer-readable storage medium is also provided, on which a computer program is stored, and when the computer program is executed by a processor, the following method is implemented:

Get the time to be positioned;

Obtain the IMU output value of the IMU at the moment to be positioned;

When receiving the first measurement signal from the 5G base station within the first predetermined time interval around the time to be positioned, determining the positioning information of the positioning device based on the IMU output value and the first measurement signal;

When the second measurement signal from the navigation satellite is received within the second predetermined time interval around the time to be positioned, the positioning information of the positioning device is determined based on the IMU output value and the second measurement signal.

In other embodiments, the above computer program also implements the positioning method of any of the above embodiments when executed by the processor.

The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction in the combination of these technical features It is considered to be the range described in this specification.

The above-mentioned embodiments only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the patent application. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.

Claims (20)

A positioning method comprising: Get the time to be positioned; Acquire the IMU output value of the IMU at the to-be-located moment; When receiving a first measurement signal from a 5G base station within a first predetermined time interval around the time to be positioned, determining the positioning information of the positioning device based on the IMU output value and the first measurement signal; When a second measurement signal from a navigation satellite is received within a second predetermined time interval around the time to be positioned, the positioning information of the positioning device is determined based on the IMU output value and the second measurement signal. The positioning method according to claim 1, wherein the to-be-located moment is an IMU sampling moment of an IMU loaded on a positioning device, and the first measurement signal includes a first 5G output value and a base station position of the 5G base station, The determining of the positioning information of the positioning device based on the IMU output value and the first measurement signal includes: Based on the first 5G output value, estimate the second 5G output value of the 5G base station at the to-be-located moment, and based on the IMU output value and the base station location, calculate the IMU at the to-be-located moment The third 5G output value of , and the positioning information of the positioning device is determined in combination with the second 5G output value and the third 5G output value. The positioning method according to claim 2, wherein the first 5G output value, the second 5G output value and the third 5G output value all include an angle of arrival and a time of arrival. The positioning method according to claim 2, wherein the first 5G output value comprises: M 5G sampling moments of the 5G base station in the first predetermined time interval, all the measured values of the 5G base station measured by the 5G base station. The M first 5G output values of the uplink reference signal of the positioning device, M≥2. The positioning method according to claim 4, wherein the estimating the second 5G output value of the 5G base station at the to-be-located moment based on the first 5G output value comprises: Based on the M 5G sampling times, the M first 5G output values, and the to-be-located time, an interpolation method is used to estimate the second 5G output value of the 5G base station at the to-be-located time. The positioning method according to claim 4, wherein the estimating the second 5G output value of the 5G base station at the to-be-located moment based on the first 5G output value comprises: At each of the to-be-located moments within the first time period after the positioning device is turned on, an interpolation method is adopted based on the M 5G sampling moments, the M first 5G output values, and the to-be-located moments Estimating the second 5G output value of the 5G base station at the to-be-located moment; During the first time period, the neural network model is trained based on a training set consisting of N 5G sampling moments in the first time period and N first 5G output values of the N 5G sampling moments. ≥2; when the training is completed and the trained neural network model is obtained, enter the second time period; At each time to be located in the second time period, the time to be located is input into the trained neural network model, and the output value of the neural network model is used as the estimated 5G base station The second 5G output value at the to-be-located moment. The positioning method according to claim 6, wherein the training of the neural network based on the training set comprises: Initializing adjustable parameters of the neural network model, the adjustable parameters include weights and bias values of the neural network model; establishing a state space model with respect to the adjustable parameters of the neural network model; Based on the state space model and the training set, using the UKF algorithm to recursively estimate the adjustable parameters, until the output error of the neural network model reaches a predetermined error range, to determine the adjustable parameters after training; and Based on the trained adjustable parameters, the trained neural network model is generated. The positioning method according to claim 2, wherein the third 5G output value of the IMU at the to-be-located moment is calculated based on the IMU output value and the base station position, and the second 5G output value is combined with the calculation value and the third 5G output value to determine the positioning information of the positioning device including: Calculate the third 5G output value of the IMU at the to-be-located moment based on the IMU output value and the base station location; Based on the positioning information of the positioning device calculated at the previous positioning time, and the IMU output value at the previous positioning time, construct the error state equation of the 5G and the IMU at the to-be-located time; Based on the second 5G output value and the third 5G output value at the to-be-located moment, construct an error observation equation of the 5G and the IMU at the to-be-located moment; The error state equations of the 5G and the IMU and the error observation equations of the 5G and the IMU are simultaneously combined, and the ESKF method is used to iteratively estimate the positioning information of the positioning device to determine the positioning information of the positioning device. The positioning method according to claim 1, wherein the to-be-located moment is an IMU sampling moment of an IMU loaded on a positioning device, and the second measurement signal includes a first satellite output value and a satellite position of the navigation satellite, The determining of the positioning information of the positioning device based on the IMU output value and the second measurement signal includes: Based on the first satellite output value, estimate the second satellite output value of the navigation satellite at the to-be-positioned moment, and based on the IMU output value and the satellite position, calculate the IMU at the to-be-positioned moment The third satellite output value of the positioning device is combined with the second satellite output value and the third satellite output value to determine the positioning information of the positioning device. The positioning method of claim 9, wherein the first satellite output value, the second satellite output value, and the third satellite output value each include pseudoranges and pseudorange rates. The positioning method according to claim 9, wherein the first satellite output value comprises: X satellite sampling moments of the navigation satellite in the second predetermined time interval, all the satellites observed by the navigation satellite X first satellite output values of the positioning device, X≥2. The positioning method according to claim 11, wherein the estimating the second satellite output value of the navigation satellite at the to-be-positioned moment based on the first satellite output value comprises: Based on the X satellite sampling times, the X first satellite output values, and the to-be-positioned time, an interpolation method is used to estimate the second satellite output value of the navigation satellite at the to-be-positioned time. The positioning method according to claim 11, wherein the estimating the second satellite output value of the navigation satellite at the to-be-positioned moment based on the first satellite output value comprises: In each of the to-be-located moments within the first time period after the positioning device is turned on, an interpolation method is adopted based on the X satellite sampling moments, the X first satellite output values, and the to-be-located moments Estimating the second satellite output value of the navigation satellite at the to-be-located moment; During the first time period, the neural network model is trained based on the training set consisting of Y satellite sampling moments and Y first satellite output values at the Y satellite sampling moments in the first time period, and Y ≥2; when the training is completed and the trained neural network model is obtained, enter the second time period; At each of the to-be-located moments in the second time period, the to-be-located moment is input into the trained neural network model, and the output value of the neural network model is used as the estimated navigation The second satellite output value of the satellite at the to-be-positioned moment. The positioning method according to claim 13, wherein the training of the neural network based on the training set comprises: Initializing adjustable parameters of the neural network model, the adjustable parameters include weights and bias values of the neural network model; establishing a state space model with respect to the adjustable parameters of the neural network model; Based on the state space model and the training set, use the UKF algorithm to recursively estimate the adjustable parameters until the output error of the neural network model reaches a predetermined error range, so as to determine the adjustable parameters after training; and Based on the trained adjustable parameters, the trained neural network model is generated. The positioning method according to claim 1, wherein the IMU output value comprises: the position, velocity and attitude of the positioning device. A positioning device, comprising: The time obtaining module is used to obtain the time to be located; An IMU value acquisition module, configured to acquire the IMU output value of the IMU at the to-be-located moment; a first positioning module, configured to, when receiving a first measurement signal from a 5G base station within a first predetermined time interval around the moment to be positioned, determine the Positioning information of the positioning device; and The second positioning module is configured to, when a second measurement signal from a navigation satellite is received within a second predetermined time interval around the to-be-positioned time, based on the IMU output value and the second measurement signal, determine the Positioning information of the positioning device. A positioning device, comprising an IMU module, a 5G module, a satellite positioning module, a memory and a processor, wherein the IMU module, the 5G module, the satellite positioning module and the memory are respectively connected to the processor; The IMU module obtains the IMU output value of the positioning device at the IMU sampling moment, and outputs the IMU output value to the processor; The 5G module receives, from the 5G base station, a first measurement signal of the uplink reference signal of the positioning device measured by the 5G base station at the 5G sampling time, and outputs the first measurement signal to the processor; The satellite positioning module receives, from a navigation satellite, a second measurement signal of the positioning device observed by the navigation satellite at the satellite sampling time, and outputs the second measurement signal to the processor; the memory stores a computer program; and When the processor executes the computer program, the positioning method according to any one of claims 1-15 is implemented. The positioning device according to claim 17, wherein the positioning device is any one of a mobile phone, a tablet computer, a portable wearable device, a vehicle, and a ship. A positioning system, comprising a 5G base station, a navigation satellite and a positioning device, wherein the positioning device is respectively connected in communication with the navigation satellite and the 5G base station; The 5G base station measures the first measurement signal of the uplink reference signal of the positioning device at the 5G sampling time, and sends the first measurement signal to the positioning device; The navigation satellite observes the second measurement signal of the positioning device at the satellite sampling moment, and outputs the second measurement signal to the positioning device; The positioning device executes the positioning method according to any one of claims 1-15. A computer-readable storage medium on which a computer program is stored, wherein when the computer program is executed by a processor, the positioning method according to any one of claims 1-15 is implemented.

Images